Patternis

Capacity-aware AI review for pull requests, with receipts.

Your provider key never reaches us. Patternis dispatches work into your GitHub Actions runner, where it uses a key held as a secret in your repository. We receive a receipt. That is the whole architecture, and it is the reason setup asks you to do two things yourself.

What it does

On a pull request, it picks a model tier by what the task needs and how much headroom your provider has left, runs the review on your runner, and posts the result. Every routing decision, refusal, and result is written to an append-only ledger you can read — including the times it declined to act, and why.

What it asks for

`metadata`	read — mandatory for every GitHub App
`pull_requests`	read — to receive the events. Not write
`issues`	write — to post the receipt where the work happened
`actions`	write — to dispatch into your own runner

It cannot modify your code. contents is not requested at all: the runner reads your diff with your own Actions token, not with the app's.

What it costs to try

15 days, no card. The AI usage during the trial is billed by your provider to your own key, on your own rate limits, because that is where it runs.

Setting it up

Installing takes one click; it will not do anything until you also add the workflow file and your provider key. The page you land on after installing walks through both. The workflow is readable in full before you install anything — it is the code that will run on your infrastructure with your key, and you should read it.

Patternis is built by Astra Forge LLC. This page is served by the Patternis service itself and reads nothing about you.